| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sun, 21 Apr 2024 08:23:12 GMT
access-control-allow-origin: *
etag: W/"6624ccf0-135da"
expires: Tue, 30 Dec 2025 08:34:56 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 561B:15317B:9D3942:B096A2:69538C58
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 08:24:56 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210051-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767083096.128968,VS0,VE203
vary: Accept-Encoding
x-fastly-request-id: b874334ce3e4290f6925a262cb95cb9dfb2e56b7
content-length: 11139
Soonmin Hwang
Soonmin Hwang
Department of Automotive Engineering, Hanyang University
I am an Assistant Professor at the Department of Automotive Engineering, Hanyang University. I was a postdoctoral researcher at the Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, United States. Before joining Carnegie Mellon, I worked for Tesla, Palo Alto, CA, United States, as a Senior Machine Learning Scientist.
I received my M.S and Ph.D. degrees in Electrical Engineering from KAIST, Korea in 2014 and 2019 respectively. During my graduate study, I worked at the Robotics and Computer Vision Lab under the supervision of Prof. In So Kweon. In 2016, I worked for Qualcomm Research, Vienna, Austria, as a Research Intern. I received Samsung HumanTech Paper Awards(Gold prize in 2017, honorable mention in 2018) and the 1st place at NVidia Korea Deep learning Contest in 2016. I received my B.S degree in Electronics and Computer Engineering from Hanyang University, Korea in 2012.
Education
-
Ph.D, 2019
Korea Advanced Institute of Science and Technology (KAIST)
-
M.S, 2014
Korea Advanced Institute of Science and Technology (KAIST)
-
B.S, 2012
Hanyang University
Interests
- Perception for Autonomous Driving
- Sensor Fusion for Robust Perception
- Path Planning and Navigation
Experience
Assistant Professor
Department of Automotive Engineering, Hanyang University
Sep 2023 –
Present
Seoul, South Korea
External Technical Advisory
42dot, Korean Autonomous Driving Company
Feb 2022 –
Present
Seoul, South Korea
Acquired by Hyundai Motor Group
Postdoc Researcher
The Robotics Institute, Carnegie Mellon University
Sep 2021 –
Aug 2023
Pittsburgh, Pennsylvania, US
Publications
SafeShift: Safety-Informed Distribution Shifts for Robust Trajectory Prediction in Autonomous Driving
IEEE Intelligent Vehicles Symposium (IV)
T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Prediction
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) [Accepted]
Instant Domain Augmentation for LiDAR Semantic Segmentation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
TransDSSL: Transformer Based Depth Estimation via Self-Supervised Learning
IEEE Robotics and Automation Letters (RA-L)
KAIST Multispectral Recognition Dataset in Day and Night
Transactions on Intelligent Transportation Systems (T-ITS)
Multispectral Transfer Network: Unsupervised Depth Estimation for All-day Vision
Association for the Advancement of Artificial Intelligence (AAAI)
Thermal Image Enhancement using Convolution Neural Network
International Conference of Intelligent Robots and Systems (IROS)
Fast Multiple Objects Detection and Tracking Fusing Color Camera and 3D LIDAR for Intelligent Vehicles
International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)
Thermal-Infrared based Drivable Region Detection
IEEE Intelligent Vehicles Symposium (IV)
Geometrical Calibration of Multispectral Calibration
International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)
Low-Cost Synchronization for Multispectral Cameras
International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)
StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
IEEE Winter Conference on Applications of Computer Vision (WACV)
All-Day Visual Place Recognition: Benchmark Dataset and Baselines
IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRw-VPRICE)
Multispectral Pedestrian Detection: Benchmark Dataset and Baselines
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
A Two Phase Approach for Pedestrian Detection
In Asian Conference on Computer Vision Workshops (ACCVw-IVVT).
Evaluation of Vocabulary Trees for Localization in Robot Applications
In International Conference on Control, Automation and Systems (ICCAS)
Patents
Object Detection Method and Apparatus in Multispectral Domain Using Multi-label Learning
Single-shot Adaptive Fusion Method and Apparatus for Robust Multispectral Object Detection
Apparatus and Method for Depth Estimation Based on Thermal Image, and Neural Network Learning Method
Method and Apparatus for Detecting Smoke from Image
Apparatus and Method for Thermal Image Enhancement
Awards
Outstanding Reviewer
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)
Jun 2023
Outstanding Reviewer (CVPR 2023)
See certificate
Research Supporting Program
KAKAO Corp.
Jun 2018
Travel grant for CVPR 2018 ($4,300) / KAKAO AI Report, Vol.14
See certificate
Research Highlights of 2017
KAIST
Mar 2018
2017 KAIST Annual R&D Report (IROS'16, AAAI'18)
See certificate
The 24th HumanTech Paper Award
Samsung Electronics, Co. Ltd
Feb 2018
Honorable mention ($2,000, top 6.5%)
See certificate
The 23rd HumanTech Paper Award
Samsung Electronics, Co. Ltd
Feb 2017
Gold prize ($10,000, top 0.7%)
See certificate
Korea Invention Patent Exhibition (KINPEX)
Korean Intellectual Property Office
Dec 2016
Bronze prize
See certificate